Multi-RBF models based prediction of component content for Pr/Nd extraction process

doi:10.11949/j.issn.0438-1157.20151950

Abstract

Abstract:

It is difficult to rapidly and accurately detect the component content in the praseodymium/neodymium (Pr/Nd) extraction process. This paper proposes a multi-RBF model and its adaptive correction method of component content. Extracting the HSI image features of Pr/Nd mixed solution, the first moments of H and S components are selected as input variables. Using the subtractive clustering algorithm, the sample data are divided into several categories and the corresponding sub-models are obtained based on RBF neural network. To further realize the high-accuracy prediction of the element component content, a parameters adjustment strategy is designed to automatically adjust the network structure and parameters of sub-models when the change of operating environment or the object characteristics results in the accuracy of the prediction model doesn't meet control requirements. The comparison experiments on actual production data from Pr/Nd extraction process show that the proposed method can meet the high-accuracy and rapid requirements of element component content detection in rare earth extraction process.

Key words: extraction process, component content, neural network, multi-models, adaptive, prediction

摘要：

针对具有特征颜色的镨/钕(Pr/Nd)萃取过程中元素组分含量难以快速准确检测的问题,提出了一种基于多RBF神经网络模型的组分含量建模及其自适应校正方法。通过选择Pr/Nd溶液图像特征H、S分量一阶矩为模型的输入变量,采用减法聚类对样本数据进行分类并建立相应的子模型;当萃取运行环境或对象特性发生变化导致模型精度不够时,根据模型参数调整策略自动调整各子模型的网络结构和参数,实现元素组分含量的准确预测。针对某Pr/Nd生产过程实际数据实验对比,结果表明本文方法能够满足稀土萃取过程元素组分含量检测的高准确度和快速性要求。

关键词: 萃取过程, 组分含量, 神经网络, 多模型, 自适应, 预测

CLC Number:

TP273

LU Rongxiu, YE Zhaobin, YANG Hui, HE Feng. Multi-RBF models based prediction of component content for Pr/Nd extraction process[J]. CIESC Journal, 2016, 67(3): 974-981.

陆荣秀, 叶兆斌, 杨辉, 何峰. 镨/钕萃取过程组分含量多RBF模型预测[J]. 化工学报, 2016, 67(3): 974-981.

References 20

[1]	杨辉, 柴天佑. 稀土分离过程综合自动化系统研究[J]. 稀有金属, 2004, 28 (6): 1071-1075. DOI: 10.3969/j.issn. 0258-7076.2004.06.024. YANG H, CHAI T Y. Integrated automation system for rare earths countercurrent extraction process[J]. Chinese Journal of Rare Mentals, 2004, 28 (6): 1071-1075. DOI: 10.3969/j.issn.0258-7076.2004.06.024.
[2]	许勇刚, 杨辉. 基于RBF网络的稀土萃取过程组分含量软测量[J]. 稀土, 2007, 28 (5): 19-22. DOI: 10.3969/j.issn.1004-0277.2007.05.005. XU Y G, YANG H. Component content soft-senor based on RBF neural network in rare earth countercurrent extraction process[J]. Chinese Rare Earths, 2007, 28 (5): 19-22. DOI: 10.3969/j.issn.1004-0277.2007.05.005.
[3]	田海, 郭智恒, 李兰云. 稀土萃取分离过程软测量方法的研究[J].中国稀土学报, 2015, 33 (2): 201-205. DOI: 10.11785/S1000-4343. 20150209. TIAN H, GUO Z H, LI L Y. Soft-sensing in rare earth extraction[J]. Journal of the Chinese Rare Earth Society, 2015, 33 (2): 201-205. DOI: 10.11785/S1000-4343. 20150209.
[4]	向峥嵘, 刘松青. 基于LS-SVM的稀土萃取组分含量软测量[J].中国稀土学报, 2009, 27 (1): 132-136. DOI: 10.3321/j.issn.1000-4343.2009.01.024. XIANG Z R, LIU S Q. Component content soft-sensor in rare earth extraction based on LS-SVM[J]. Journal of the Chinese Rare Earth Society, 2009, 27 (1): 132-136. DOI: 10.3321/j.issn.1000-4343.2009. 01.024.
[5]	贾文君, 柴天佑. 稀土串级萃取分离过程元素组分含量的多模型软测量[J]. 控制理论与应用, 2007, 24 (4): 569-573. DOI: 10.3969/j.issn.1000-8152.2007.04.011. JIA W J, CHAI T Y. Soft-sensor of element component content based on multiple models for the rare earth cascade extraction process[J]. Control Theory & Applications, 2007, 24 (4):569-573. DOI: 10.3969/j.issn.1000-8152.2007.04.011.
[6]	李修亮, 苏宏业, 褚健. 基于在线聚类的多模型软测量建模方法[J]. 化工学报, 2007, 58 (11): 2834-2839. DOI: 10.3321/j.issn:0438-1157.2007.11.025. LI X L, SU H Y, CHU J. Multiple models soft-sensing technique based on online clustering arithmetic[J]. Journal of Chemical Industry and Engineering (China), 2007, 58 (11): 2834-2839. DOI: 10.3321/j.issn. 0438-1157.2007.11.025.
[7]	杜文莉, 官振强, 钱锋. 一种基于时序误差补偿的动态软测量建模方法[J]. 化工学报, 2010, 61 (2): 439-443. DU W L, GUAN Z Q, QIAN F. Dynamic soft sensor modeling based on time series error compensation[J]. CIESC Journal, 2010, 61 (2): 439-443.
[8]	杨辉, 高子洁, 陆荣秀. 基于稀土离子颜色特征识别的组分含量检测方法[J]. 中国稀土学报, 2012, 30 (1): 108-112. YANG H, GAO Z J, Lu R X. Detection method of component content based on rare earth ions color characteristics identification[J]. Journal of the Chinese Rare Earth Society, 2012, 30 (1): 108-112.
[9]	陆荣秀, 杨辉, 欧阳超明, 等. 基于PCA-LS_SVM的镨/钕萃取过程元素组分含量预测[J]. 南昌大学学报 (理科版), 2013, 37 (6): 589-593. DOI: 10.3969/j.issn.1006-0464. 2013.06.018. LU R X, YANG H, OUYANG C M, et al. Forecast of element component content in Pr/Nd extraction process based on PCA-LS_SVM[J]. Journal of Nanchang University (Natural Science), 2013, 37 (6): 589-593. DOI: 10.3969/j.issn.1006-0464. 2013.06.018.
[10]	柴天佑, 杨辉.稀土萃取分离过程自动控制研究现状及发展趋势[J].中国稀土学报, 2004, 22 (4): 427-433. DOI: 10.3321/j.issn:1000-4343.2004.04.001. CHAI T Y, YANG H. Situation and developing trend of rare-earth countercurrent extraction processes control[J]. Journal of the Chinese Rare Earth Society, 2004, 22 (4): 427-433. DOI: 10.3321/j.issn:1000-4343.2004.04.001.
[11]	HUANG M Z, WAN J Q, MA Y W, et al. A fast predicting neural fuzzy model for online estimation of nutrient dynamics in an anoxie/oxic process[J]. Bioresource Technology, 2010, 101 (6): 1642-1651.
[12]	ALTUNAY P, SEVER A, SERDAR S G, et al. Prediction of effluent quality of an anaerobic treatment plant under unsteady state through ANFIS modeling with online input variables[J]. Chemical Engineering Journal, 2008, 145 (1): 78-85.
[13]	唐志杰, 唐朝晖, 朱红求. 一种基于多模型融合软测量建模方法[J]. 化工学报, 2011, 62 (8): 2248-2252. DOI: 10.3969/j.issn.0438-1157.2011.08.028. TANG Z J, TANG Z H, ZHU H Q. A multi-model fusion soft sensor modeling method[J]. CIESC Journal, 2011, 62 (8): 2248-2252. DOI: 10.3969/j.issn.0438-1157.2011.08.028.
[14]	张昭昭, 乔俊飞. 基于在线减法聚类的RBF神经网络结构设计[J]. 控制与决策, 2012, 27 (7): 997-1002. ZHANG Z Z, QIAO J F. Design RBF neural network architecture based on online subtractive clustering[J]. Control and Decision, 2012, 27 (7): 997-1002.
[15]	陆荣秀, 欧阳超明, 杨辉, 等. HSI颜色模型在镨钕组分含量检测中的应用[J]. 计算机与应用化学, 2013, 30 (10): 1157-1161. DOI: 10.3969/j.issn.1001-4160.2013. 10.016. LU R X, OUYANG C M, YANG H, et al. Pr/Nd component content detection using a HSI color model[J]. Computers and Applied Chemistry, 2013, 30 (10): 1157-1161. DOI: 10.3969/j.issn.1001-4160.2013. 10.016.
[16]	XIONG S W, NIU X X, LIU H B. Support vector machines based on subtractive clustering[C]//Proceeding of the Fourth International Conference on Machine Learning and Cybernetics, 2005: 43-45.
[17]	潘天红, 薛振框, 李少远. 基于减法聚类的多模型在线辨识算法[J]. 自动化学报, 2009, 35 (2): 220-224. DOI: 10.3724/SP.J.1004. 2009.00220. PAN T H, XUE Z K, LI S Y. An online multi-model identification algorithm based on subtractive clustering[J]. Acta Automatica Sinica, 2009, 35 (2): 220-224. DOI: 10.3724/SP.J.1004.2009.00220.
[18]	魏海坤, 宋文忠, 李奇. 基于RBF网络的火电机组实时成本在线建模方法[J]. 中国电机工程学报, 2004, 24 (7): 250-256. DOI: 10.3321/j.issn:0258-8013.2004.07. 047. WEI H K, SONG W Z, LI Q. A RBF network based online modeling method for realtime cost model in power plant[J]. Proceedings of the CSEE, 2004, 24 (7): 250-256. DOI: 10.3321/j.issn:0258-8013.2004.07. 047.
[19]	乔俊飞, 韩红桂. RBF神经网络的结构动态优化设计[J]. 自动化学报, 2010, 36 (6): 865-872. DOI: 10.3724/SP.J. 1004.2010.00865. QIAO J F, HAN H G. Optimal structure design for RBFNN structure[J]. Acta Automatica Sinica, 2010, 36 (6): 865-872. DOI: 10.3724/SP.J.1004.2010.00865.
[20]	HAO C, YU G, XIA H. Online modeling with tunable RBF network[J]. IEEE Transactions on Cybernetics, 2013, 43 (3): 935-947.